Claude Code

Claude Code speaks the Anthropic Messages API. We run that API at POST /v1/messages, so a base URL and a key are the whole integration. Claude Code gives you nowhere to set start_within, so the deadline goes on an agent key. An interactive session streams, and Claude’s cheaper tier doesn’t, so pick a tier rather than Flex race. The race rules are on Flex Racing with Claude models. Your organization needs Anthropic servable first: an Anthropic provider key on your own keys, or Anthropic turned on and funded on Managed Keys.

Set this up with an agent

Copy the block below into any coding agent. It never asks for your API key: you run the one export line yourself.

Copy agent setup prompt

Configure Claude Code to send its requests to FlexInference, which serves the Anthropic Messages API.

You will never see or handle my API key. Claude Code reads it from the `ANTHROPIC_AUTH_TOKEN` environment variable, and I export that myself. Do not ask me for the key, do not write it into any file, and do not read it from my environment.

Ask me whether to configure this globally or for one project, then edit `~/.claude/settings.json` or `.claude/settings.json` accordingly. Create the file if it does not exist, and preserve every setting already in it.

Add this `env` block, merging into any existing `env` rather than replacing it. Note that it carries no credential:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.flexinference.com",
    "ANTHROPIC_MODEL": "claude-opus-5",
    "ANTHROPIC_SMALL_FAST_MODEL": "claude-haiku-4-5",
    "CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS": "1"
  }
}

Then print this line for me to run in the shell I start Claude Code from. Do not run it and do not ask for the value:

export ANTHROPIC_AUTH_TOKEN=<paste your key here>

Rules that matter, do not deviate:
- `ANTHROPIC_BASE_URL` must NOT end in `/v1`. Claude Code appends `/v1/messages` itself.
- The credential must arrive as `ANTHROPIC_AUTH_TOKEN`, never `ANTHROPIC_API_KEY`. The first sends `Authorization: Bearer`, which FlexInference requires. The second sends `x-api-key`, which it refuses with `401 missing_api_key`.
- Both model variables must be `claude-*` slugs. Claude Code sends Anthropic-native fields such as `output_config` on every request, and FlexInference refuses to mistranslate them onto a non-Claude model.
- `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` must be `"1"`. Without it Claude Code sends experimental beta fields such as `context_management`, FlexInference does not forward the `anthropic-beta` headers they need, and every request fails with `400 context_management: Extra inputs are not permitted`.
- Do not add a retry setting. Claude Code retries on its own and my key may carry its own policy.

Finally, tell me that Anthropic must be servable on my FlexInference organization. On BYOK that means an Anthropic provider key on the API, then Provider keys tab. On Managed Keys it means Anthropic enabled and funded. Then start a new Claude Code session and report what you changed.

Configure Claude Code

Create or open ~/.claude/settings.json. A per-project file at .claude/settings.json works the same way.

Add an env block naming the router, your key, and both models.

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.flexinference.com",
    "ANTHROPIC_AUTH_TOKEN": "flex_live_...",
    "ANTHROPIC_MODEL": "claude-opus-5",
    "ANTHROPIC_SMALL_FAST_MODEL": "claude-haiku-4-5",
    "CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS": "1"
  }
}

Start Claude Code.
claude

Export the same variables in your shell instead, to keep the secret out of a file.

export ANTHROPIC_BASE_URL=https://api.flexinference.com
export ANTHROPIC_AUTH_TOKEN=flex_live_...
export CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1

Four rules make this work. Omit the /v1 suffix. Claude Code appends /v1/messages to the base URL itself. Use ANTHROPIC_AUTH_TOKEN, never ANTHROPIC_API_KEY. The first sends Authorization: Bearer, which we require. The second sends x-api-key, which we refuse. Set CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS to 1. Claude Code otherwise sends experimental beta fields such as context_management. We don’t forward the anthropic-beta headers those fields need, so every request fails. Set both model variables. Claude Code runs a large main-loop model and a small background model against one key. Both must be claude-* slugs.

Troubleshooting

400 context_management: Extra inputs are not permitted. Claude Code sent an experimental beta field, and we don’t forward the anthropic-beta header it needs. Set CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 and start a new session. The same flag clears any other Extra inputs are not permitted refusal naming a beta field. 401 missing_api_key. You set ANTHROPIC_API_KEY, so the client sent x-api-key, which we don’t read. Set ANTHROPIC_AUTH_TOKEN instead and unset ANTHROPIC_API_KEY. 400 unsupported_parameter naming output_config. A model variable points at a non-Claude slug, and Claude Code sends Anthropic-native fields we refuse to mistranslate. Set both model variables to claude-* slugs. 404 unknown_url naming /v1/messages/count_tokens. We don’t route that path. A claude -p run never calls it, though an interactive session may. Anything not specific to Claude Code is on agent keys.

Get started

Concepts

Additional Features

Using the API

Agent Keys + Integrations

Set this up with an agent

Configure Claude Code

Troubleshooting

​Set this up with an agent

​Configure Claude Code

​Troubleshooting

Set this up with an agent

Configure Claude Code

Troubleshooting